From 172a3152b42af36443ec6a0a39969471c35b893d Mon Sep 17 00:00:00 2001
From: maliubiao <maliubiao@gmail.com>
Date: 星期日, 29 十二月 2024 22:33:22 +0800
Subject: [PATCH] 允许 model.generate 使用bytes io, 以便不写入文件，节省io时间 (#2343)
---
runtime/onnxruntime/src/ct-transformer-online.cpp | 7 ++++++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/runtime/onnxruntime/src/ct-transformer-online.cpp b/runtime/onnxruntime/src/ct-transformer-online.cpp
index 769bb65..83c0327 100644
--- a/runtime/onnxruntime/src/ct-transformer-online.cpp
+++ b/runtime/onnxruntime/src/ct-transformer-online.cpp
@@ -42,6 +42,11 @@
vector<int> InputData;
string strText; //full_text
strText = accumulate(arr_cache.begin(), arr_cache.end(), strText);
+
+ // 濡傛灉涓婁竴鍙ョ殑缁撳熬鏄嫳璇瓧姣嶏紝骞朵笖杩欎竴鍙ョ殑寮�濮嬩篃鏄嫳璇瓧姣嶏紝搴旇娣诲姞绌烘牸
+ if ((strText.size() > 0 and !(strText[strText.size()-1] & 0x80)) && (strlen(sz_input) > 0 && !(sz_input[0] & 0x80)))
+ strText += " ";
+
strText += sz_input; // full_text = precache + text
m_tokenizer.Tokenize(strText.c_str(), strOut, InputData);
@@ -107,7 +112,7 @@
{
if (!(sentence_words_list[i][0] & 0x80) && (i + 1) < sentence_words_list.size() && !(sentence_words_list[i + 1][0] & 0x80))
{
- sentence_words_list[i] = " " + sentence_words_list[i];
+ sentence_words_list[i] = sentence_words_list[i] + " ";
}
if (nSkipNum < arr_cache.size()) // if skip_num < len(cache):
nSkipNum++;
--
Gitblit v1.9.1